Hybrid Machine Learning Approaches and Applications


General Information

  • Offered by: UMTL (Chair of Prof. Dr. Antonio Krüger)
  • Lecturers: Michael FeldGuillermo ReyesAmr Gomaa, Matthias Klusch
  • Location: Due to the COVID-19 crisis the seminar will take place online-only
  • Time: Wednesdays 10:00-12:00 
  • Credit Points: 7
  • Language: English
  • Places:12


  • The kickoff session will be on the 4th of November. Presence on that day is strictly mandatory. A link to the meeting will follow shortly.

Knowledge and Data together form the foundation of most AI systems: Symbolic or Semantic knowledge forms concepts and relations describing structures in a logical and human-interpretable way, allowing queries, reasoning and inference. Sub-symbolic or Syntactic Data is little or non-structured sensor data, such as images or audiothat has high volume and is harder to interpret or program against by humans in their raw form. 

While there are often connections between them, they both have their own techniques for learning and adapting models, and this is done mostly separately today. Considering recent advances in deep learning, researchers are now reviewing existing and developing new methods for hybrid learning. where knowledge and data are used in conjunction to train inter-linked models that offer both the predictive strength and efficiency of data-based models, as well as the structure and transparency of knowledge-based models. 

In this seminar, we are going to review 

  • The current state of symbolic and sub-symbolic representation and learning methods 

  • Hybrid learning approaches where sub-symbolic training can be improved by symbolic knowledge and vice versa 

  • Models that merge symbolic and sub-symbolic parts 

  • Applications where hybrid learning provides benefits

Important Note: 
Due to the tremendously increasing interest in the future-oriented AI research area of hybrid learning and reasoning, we decided to offer more places for students by the twin seminars HyLEAR (Hybrid Learning and Reasoning) and HMLA (Hybrid Machine Learning Approaches and Applications) with complimentary topics in this area. We highly recommend all interested participants to register for both twin seminars in the SIC seminar assignment system (you will be assigned effectively to one of both but can visit the other).
More info on our twin seminar HyLEAR: http://www.dfki.de/~klusch/HyLEAR-seminar-ws20